Neural-Davidsonian Semantic Proto-role Labeling

2018/04/21 by Rudinger, Rachel, Teichert, Adam, Culkin, Ryan +2 · 1 citation
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1804.07976

Abstract

We present a model for semantic proto-role labeling (SPRL) using an adapted bidirectional LSTM encoding strategy that we call "Neural-Davidsonian": predicate-argument structure is represented as pairs of hidden states corresponding to predicate and argument head tokens of the input sequence. We demonstrate: (1) state-of-the-art results in SPRL, and (2) that our network naturally shares parameters between attributes, allowing for learning new attribute types with limited added supervision.

Cited by

• Do We Really Need GNNs with Explicit Structural Modeling? MLPs Suffice for Language Model Representations

Related

• Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling
• Multi-Task Learning for Joint Semantic Role and Proto-Role Labeling
• End-to-end Semantic Role Labeling with Neural Transition-based Model
• Dependency and Span, Cross-Style Semantic Role Labeling on PropBank and NomBank
• An Argument-Marker Model for Syntax-Agnostic Proto-Role Labeling